From 5ea9777b39ecc69864df040bec2c3af9c7204f88 Mon Sep 17 00:00:00 2001
From: Michele Pagot <michele.pagot@suse.com>
Date: Fri, 13 Sep 2024 16:04:03 +0200
Subject: [PATCH] Delay the crash system command

One of the HanaSR test is about crashing one cluster node running HANA.
Crash command is executed through a ssh channel. Problem is that, as soon as the
system crash, the ssh connection  is interrupted leaving the ssh client blocked.
The idea is: compose the remotely executed command with a sleep and then the crash,
run these two in background. It gives time to the ssh client to close the
session before the crash happening.
Remove the timepout=0 behavior, stop forwarding to run_ssh_command all
the args content.
---
 lib/sles4sap_publiccloud.pm | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/lib/sles4sap_publiccloud.pm b/lib/sles4sap_publiccloud.pm
index 3f0588524f01..b2b2a92dbfdd 100644
--- a/lib/sles4sap_publiccloud.pm
+++ b/lib/sles4sap_publiccloud.pm
@@ -369,9 +369,12 @@ sub stop_hana {
     my %commands = (
         stop => 'HDB stop',
         kill => 'HDB kill -x',
+        # -b is for running the command in background
         # echo b > /proc/sysrq-trigger is for crashing the remote node
+        # sleep 5 is to give time sudo to put the command execution in background and
+        # to ssh to return, both before to trigger the crash
         # This also work in conjunction with ssh -fn arguments
-        crash => 'sudo su -c "echo b > /proc/sysrq-trigger &"'
+        crash => 'sudo -b sh -c "sleep 5; echo b > /proc/sysrq-trigger"'
     );
     croak("HANA stop method '$args{method}' unknown.") unless $commands{$args{method}};
 
@@ -400,7 +403,8 @@ sub stop_hana {
             cmd => $cmd,
             # This timeout is to ensure the run_ssh_command is executed in a reasonable amount of time.
             # It is not about how much time the crash is expected to take in the SUT.
-            # Also consider that internally run_ssh_command is using this value for two different guard mechanisms.
+            # Expect run_ssh_command to return immediately, and 10 has nothing to do with the value of sleep 5 executed remotely.
+            # Also consider that internally run_ssh_command is using this value for two different guard mechanism.
             timeout => 10,
             # This test does not care about output,
             # setting this in conjunction with timeout >0 result in the internal implementation of
@@ -408,6 +412,13 @@ sub stop_hana {
             rc_only => 1,
             ssh_opts => $crash_ssh_opts);
 
+        # crash trigger command:
+        #  - is executed in background
+        #  - has sleep 5 executed remotely.
+        # run_ssh_command return immediately, so before the remote system execute the crash command.
+        # So the test execution has to sleep now, waiting that remote system has time to execute the crash procedure.
+        sleep 10;
+
         # Wait till ssh disappear
         record_info("Wait ssh disappear start");
         my $out = $self->{my_instance}->wait_for_ssh(timeout => 60, wait_stop => 1);